[Mplayer-dev-eng] projectmayo's divx codec...

[Arpi]

Hi,

Just tested the first beta of Projectmayo's new divx 3.11 (ms-mpeg4v3) and
4.0 (opendivx 0.48) codec:

Coyote.Ugly.Sample-highbitrate-atmos.avi
VIDEO:  [DIV3]  640x480  24bpp  25.00 fps  1995.1 kbps (243.5 kbyte/s)

Forcing video codec: [odivx] drv:3 (OpenDivX (MPEG-4 v2))
BENCHMARKs: V:  13.281s VO:   3.889s A:   0.000s Sys:   0.344s =   17.514s
BENCHMARK%: V: 75.8326% VO: 22.2039% A:  0.0000% Sys:  1.9635% = 100.0000%

Forcing video codec: [divxds] drv:4 (DivX ;-) (MS MPEG-4 v3))
BENCHMARKs: V:  19.906s VO:   4.945s A:   0.000s Sys:   0.338s =   25.189s
BENCHMARK%: V: 79.0280% VO: 19.6300% A:  0.0000% Sys:  1.3420% = 100.0000%

Forcing video codec: [divx] drv:2 (DivX ;-) (MS MPEG-4 v3))
BENCHMARKs: V:  19.341s VO:   4.852s A:   0.000s Sys:   0.342s =   24.535s
BENCHMARK%: V: 78.8304% VO: 19.7760% A:  0.0000% Sys:  1.3936% = 100.0000%

Forcing video codec: [ffdivx] drv:5 (FFmpeg DivX ;-) (MS MPEG-4 v3))
BENCHMARKs: V:  22.831s VO:   3.821s A:   0.000s Sys:   0.340s =   26.992s
BENCHMARK%: V: 84.5855% VO: 14.1564% A:  0.0000% Sys:  1.2582% = 100.0000%

Strange results. I can't imagine how can it be so fast.
Btw their binary (it is binary-only, and symbols stripped;() has lot's
of mmx/sse code. And _maybe_ they used some optimizing compiler for
compiling (Intel's or visual c), not gcc...


A'rpi / Astral & ESP-team

--
mailto:arpi at thot.banki.hu
http://esp-team.scene.hu

_______________________________________________
Mplayer-dev-eng mailing list
Mplayer-dev-eng at lists.sourceforge.net
http://lists.sourceforge.net/lists/listinfo/mplayer-dev-eng